Metraipolis › archive › dc_2adf6fd49dcb
Expected Sample Complexity in Multi-Armed Bandits — arXiv:2610.09929
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09929
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:35:57.683Z
- SHA-256 of the archived text
5a7d1b002018e8700cb68127344f103a3d33d86d62d4c5b1dbde2a90ccd43441- Stable URL of this page
https://metraipolis.com/documento/dc_2adf6fd49dcb
How to cite
Expected Sample Complexity in Multi-Armed Bandits — arXiv:2610.09929 — arXiv (en), https://arxiv.org/abs/2610.09929 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2adf6fd49dcb (Metraipolis archive dc_2adf6fd49dcb, sha256 5a7d1b002018e8700cb68127344f103a3d33d86d62d4c5b1dbde2a90ccd43441)
BibTeX
@misc{dc2adf6fd49dcb,
title = {Expected Sample Complexity in Multi-Armed Bandits — arXiv:2610.09929},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09929},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2adf6fd49dcb; sha256 5a7d1b002018e8700cb68127344f103a3d33d86d62d4c5b1dbde2a90ccd43441},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09929. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sample complexity is a widely used metric in sequential decision-making problems, defined as the number of suboptimal decisions during the interaction between the agent and an environment. We study the sample complexity of stochastic multi-armed bandit problems and introduce the expected sample complexity performance measure, analyzing it in a novel framework called approximately correct in expectation (ACE). We show that ACE guarantees imply almost sure convergence to the optimal expected reward, in contrast to high-probability guarantees found in other frameworks, and also show how to convert ACE guarantees into explicit expected regret bounds. We further show that, in contrast to existing measures, deterministic algorithms cannot obtain favorable ACE bounds, and analyze stochastic algorithms in two settings: when the allowed suboptimality level $\epsilon$ is known to the algorithm and when it is unknown. In the former, we devise an explore-then-$\epsilon$-greedy algorithm, and in the latter, we analyze the expected sample complexity of Thompson sampling. Finally, we establish nearly matching lower bounds for both settings, showing that the algorithms are tight in $\epsilon$ and proving a performance separation between the two regimes. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.09929 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T12:14:15.290Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).